Paper: arXiv 2510.04556

Authors: Alexej Brauer, Paul Menzel, Mario V. Wüthrich

Abstract

Maintaining the predictive performance of pricing models is challenging when insurance portfolios and data-generating mechanisms evolve over time. Focusing on non-life insurance, we adopt the concept-drift terminology from machine learning and distinguish virtual drift from real concept drift in an actuarial setting. Methodologically, we (i) formalize deviance loss and Murphy’s score decomposition to assess global and local auto-calibration; (ii) study the Gini score as a rank-based performance measure, derive its asymptotic distribution, and develop a consistent bootstrap estimator of its asymptotic variance; and (iii) combine these results into a statistically grounded, model-agnostic monitoring framework that integrates a Gini-based ranking drift test with global and local auto-calibration tests. An application to a modified motor insurance portfolio with controlled concept-drift scenarios illustrates how the framework guides decisions on refitting or recalibrating pricing models.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a statistically grounded framework with advanced derivations, such as the asymptotic distribution of the Gini score and Murphy’s decomposition, indicating high mathematical density. It demonstrates empirical applicability through a controlled concept-drift simulation on a modified motor insurance portfolio, showing data-heavy implementation and backtest-ready guidance.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Monitor Pricing Model Performance under<br>Concept Drift in Non-Life Insurance"] --> B["Methodology Development"]
  
  subgraph B ["Key Methodology Steps"]
      B1["Formalize Deviance Loss<br>Murphy Score Decomposition<br>Global & Local Auto-calibration"]
      B2["Analyze Gini Score<br>Asymptotic Distribution<br>Bootstrap Variance Estimator"]
      B3["Integrate Framework<br>Gini Ranking Drift Test +<br>Auto-calibration Tests"]
  end
  
  B --> C["Data & Inputs<br>Motor Insurance Portfolio<br>Simulated Concept Drift Scenarios"]
  
  C --> D["Computational Processes<br>Statistical Tests + Model-Agnostic<br>Drift Detection"]
  
  D --> E["Key Findings & Outcomes<br>1. Distinguished Virtual vs Real Drift<br>2. Consistent Bootstrap Estimator<br>3. Framework for Refit/Recalibration Decisions"]

Cited References (105)

  1. LightGBM : A Highly Efficient Gradient Boosting Decision Tree (2017) — link
  2. Predictive Learning via Rule Ensembles (2008) — link
  3. Nesting Classical Actuarial Models into Neural Networks (2019) — link
  4. EDITORIAL : YES , WE CANN ! (2019) — link
  5. From Generalized Linear Models to Neural Networks , and Back (2019) — link
  6. AI : Coming of Age ? (2022) — link
  7. SHAP for Actuaries : Explain any Model (2023) — link
  8. Enhancing Logistic Regression Using Neural Networks for Classification in Actuarial Learning (2023) — link
and 97 more
  1. LocalGLMnet : Interpretable Deep Learning for Tabular Data (2023) — link
  2. Entity Embeddings of Categorical Variables (2016) — link
  3. Embeddings for Tabular Data : A Survey (2023) — link
  4. Revisiting Deep Learning Models for Tabular Data (2021) — link
  5. On Embeddings for Numerical Features in Tabular Deep Learning (2022) — link
  6. A Unified Approach to Interpreting Model Predictions (2017) — link
  7. Statistical Foundations of Actuarial Learning and Its Applications (2023) — link
  8. Combined Actuarial Neural Networks in Actuarial Rate Making (2021) — link
  9. Neural Network Theory (2022) — link
  10. Attention is All you Need (2017) — link
  11. Why do Tree -based Models Still Outperform Deep Learning on Typical Tabular Data ? (2022) — link
  12. Believing the Bot - Model Risk in the Era of Deep Learning (2019) — link
  13. Generalized Linear Models (1972) — link
  14. Greedy Function Approximation : A Gradient Boosting Machine (2001) — link
  15. Generalized Linear Models (1983)
  16. Deep Learning (2016)
  17. Generalized Additive Models (1986) — link
  18. Generalized Additive Models (1990)
  19. Deep Residual Learning for Image Recognition (2016) — link
  20. Bayesian Deep Net GLM and GLMM (2020) — link
  21. TabNet : Attentive Interpretable Tabular Learning (2021) — link
  22. TabPFN : A Transformer That Solves Small Tabular Classification Problems in a Second (2023) — link
  23. TabR : Unlocking the Power of Retrieval - Augmented Tabular Deep Learning (2023) — link
  24. Varying- Coefficient Models (1993) — link
  25. TabTransformer : Tabular Data Modeling Using Contextual Embeddings (2020) — link
  26. The Transformer Model in Equations — link
  27. CASdatasets : Insurance Datasets (2018) — link
  28. Peeking into the Black Box : An Actuarial Case Study for Interpretable Machine Learning (2020) — link
  29. Case Study : French Motor Third - Party Liability Claims (2020) — link
  30. GLU Variants Improve Transformer (2020) — link
  31. Delving Deep into Rectifiers : Surpassing Human - Level Performance on ImageNet Classification (2015) — link
  32. The Balance Property in Neural Network Modelling (2022) — link
  33. CASdatasets : Insurance Datasets (2018) — link
  34. API Design for Machine Learning Software : Experiences from the Scikit - Learn Project (2013)
  35. Python 3 Reference Manual (2009)
  36. TensorFlow : Large-Scale Machine Learning on Heterogeneous Systems (2015) — link
  37. The Balance Property in Insurance Pricing (2025) — link
  38. Optuna: A Next -generation Hyperparameter Optimization Framework (2019)
  39. A Multi -task Network Approach for Calculating Discrimination -free Insurance Prices (2023) — link
  40. Rethinking Representations in P & C Actuarial Science with Deep Neural Networks (2021) — link
  41. The Use of Autoencoders for Training Neural Networks with Mixed Categorical and Numerical Features (2023) — link
  42. Neural Networks for Insurance Pricing with Frequency and Severity Data : A Benchmark Study from Data Preprocessing to Technical Tariff (2025) — link
  43. AI in Actuarial Science – a Review of Recent Advances – Part 1 (2021) — link
  44. Non-life Insurance Risk Classification Using Categorical Embedding (2023) — link
  45. Embeddings and Attention in Predictive Modeling (2021) — link
  46. SHAPNN : Shapley Value Regularized Tabular Neural Network (2023) — link
  47. LASSO regularization within the LocalGLMnet architecture (2023) — link
  48. The Problem of Concept Drift : Definitions and Related Work (2004) — link
  49. Enhancing Actuarial Non -life Pricing Models via Transformers — → 2311.07597
  50. Smoothness and Monotonicity Constraints for Neural Networks Using ICEnet (2023) — link
  51. Model Selection with Gini Indices under Auto -calibration (2023) — link
  52. Insurance, Biases , Discrimination and Fairness (2024) — link
  53. Testing for Auto -calibration with Lorenz and Concentration Curves (2024) — link
  54. Autocalibration and Tweedie -dominance for Insurance Pricing with Machine Learning (2021) — link
  55. Generic Conditions for Forecast Dominance (2021) — link
  56. The Credibility Transformer (2025) — link
  57. Beyond Incremental Processing : Tracking Concept Drift (1986)
  58. The Bootstrap and Edgeworth Expansion (1992) — link
  59. Learning in the Presence of Concept Drift and Hidden Contexts (1996) — link
  60. Learning with Drift Detection (2004) — link
  61. All of Nonparametric Statistics (2006) — link
  62. Detecting Concept Drift Using Statistical Testing (2007) — link
  63. Learning from Time - Changing Data with Adaptive Windowing (2007) — link
  64. Reliable Inference for the Gini Index (2009) — link
  65. A Survey on Concept Drift Adaptation (2014) — link
  66. Failing Loudly : An Empirical Study of Methods for Detecting Dataset Shift (2019)
  67. Model Selection Based on Lorenz and Concentration Curves , Gini Indices and Convex Order (2019) — link
  68. Learning under Concept Drift : A Review (2019) — link
  69. Automatically Detecting Data Drift in Machine Learning Classifiers (2021) — link
  70. Asymptotics of the Bootstrap via Stability with Applications to Inference with Model Selection (2021) — link
  71. Matchmaker: Data Drift Mitigation in Machine Learning for Large -scale Systems (2022) — link
  72. Concept Drift Detection Based on Deep Neural Networks and Autoencoders (2025) — link
  73. One or Two Things we Know about Concept Drift —a Survey on Monitoring in Evolving Environments . Part A : Detecting Concept Drift (2024) — link
  74. One or Two Things we Know about Concept Drift —a Survey on Monitoring in Evolving Environments . Part B : Locating and Explaining Concept Drift (2024) — link
  75. AI Tools for Actuaries (2025) — link
  76. Predicting Accurate Probabilities with a Ranking Loss (2012)
  77. Auto-calibration Tests for Discrete Finite Regression Functions (2025) — link
  78. Asymptotic Statistics (1998) — link
  79. Weak Convergence and Empirical Processes : With Applications to Statistics (2023) — link
  80. Convergence of Probability Measures (1999) — link
  81. Isotonic Regression for Variance Estimation and Its Role in Mean Estimation and Model Validation (2025) — link
  82. Universal Inference for Testing Calibration of Mean Estimates within the Exponential Dispersion Family (2025) — link
  83. Gini Score under Ties and Case Weights (2025) — link
  84. Stable Reliability Diagrams for Probabilistic Classifiers (2021) — link
  85. Isotonic Recalibration under a Low Signal -to-noise Ratio — → 2301.02692
  86. Regression Diagnostics Meets Forecast Evaluation : Conditional Calibration , Reliability Diagrams , and Coefficient of Determination (2023) — link
  87. Some Properties of Exponential Dispersion Models (1986) — link
  88. Exponential Dispersion Models (1987) — link
  89. A New Vector Partition of the Probability Score (1973) — link
  90. General Decompositions of MSE - Based Skill Scores : Measures of Some Basic Aspects of Forecast Quality (1996) — link
  91. The Isotonic Regression Problem and Its Dual (1972) — link
  92. Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves : A Nonparametric Approach (1988) — link
  93. Strictly Proper Scoring Rules , Prediction , and Estimation (2007) — link
  94. Making and Evaluating Point Forecasts (2011) — link
  95. Statistical Inference Under Order Restrictions : The Theory and Application of Isotonic Regression (1972)
  96. Insurance Ratemaking and a Gini Index (2014) — link
  97. Summarizing Insurance Scores Using a Gini Index (2011) — link

2 of 105 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.